Add model and its dependencies

.gitattributes

@@ -9,6 +9,7 @@
 *.lfs.* filter=lfs diff=lfs merge=lfs -text
 *.model filter=lfs diff=lfs merge=lfs -text
 *.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
 *.onnx filter=lfs diff=lfs merge=lfs -text
 *.ot filter=lfs diff=lfs merge=lfs -text
 *.parquet filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,80 @@
+---
+language:
+- en
+license: apache-2.0
+tags:
+- generated_from_trainer
+datasets:
+- ''
+metrics:
+- accuracy
+model-index:
+- name: SEED0042
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: MNLI
+      type: ''
+      args: mnli
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.8572592969943963
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# SEED0042
+
+This model is a fine-tuned version of [bert-large-uncased](https://huggingface.co/bert-large-uncased) on the MNLI dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.5092
+- Accuracy: 0.8573
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 5e-05
+- train_batch_size: 1
+- eval_batch_size: 1
+- seed: 42
+- distributed_type: not_parallel
+- gradient_accumulation_steps: 32
+- total_train_batch_size: 32
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 2000
+- num_epochs: 3
+
+### Training results
+
+| Training Loss | Epoch | Step  | Validation Loss | Accuracy |
+|:-------------:|:-----:|:-----:|:---------------:|:--------:|
+| 0.4736        | 1.0   | 12271 | 0.4213          | 0.8372   |
+| 0.3248        | 2.0   | 24542 | 0.4055          | 0.8538   |
+| 0.1571        | 3.0   | 36813 | 0.5092          | 0.8573   |
+
+
+### Framework versions
+
+- Transformers 4.17.0
+- Pytorch 1.10.0+cu113
+- Datasets 2.1.0
+- Tokenizers 0.11.6

all_results.json

@@ -0,0 +1,20 @@
+{
+    "epoch": 3.0,
+    "train_loss": 0.33884849047837634,
+    "train_runtime": 68835.7532,
+    "train_samples": 392702,
+    "train_samples_per_second": 17.115,
+    "train_steps_per_second": 0.535,
+    "validation-m_accuracy": 0.8572592969943963,
+    "validation-m_loss": 0.5091902017593384,
+    "validation-m_runtime": 128.2797,
+    "validation-m_samples": 9815,
+    "validation-m_samples_per_second": 76.512,
+    "validation-m_steps_per_second": 76.512,
+    "validation-mm_accuracy": 0.8581163547599675,
+    "validation-mm_loss": 0.5057684779167175,
+    "validation-mm_runtime": 129.1109,
+    "validation-mm_samples": 9832,
+    "validation-mm_samples_per_second": 76.152,
+    "validation-mm_steps_per_second": 76.152
+}

config.json

@@ -0,0 +1,38 @@
+{
+  "_name_or_path": "bert-large-uncased",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "finetuning_task": "mnli",
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "entailment",
+    "1": "neutral",
+    "2": "contradiction"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "contradiction": 2,
+    "entailment": 0,
+    "neutral": 1
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.17.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f048a84b6b6c8c0100cc443d6362826f7d22a4e101617d666b6287ee8fa060a
+size 1340743405

run_arguments.json

@@ -0,0 +1,25 @@
+{
+    "model_name_or_path": "bert-large-uncased",
+    "task_name": "mnli",
+    "output_dir": "./output/bert-large/mnli/0001/SEED0042/",
+    "learning_rate": 5e-05,
+    "num_train_epochs": 3,
+    "per_device_eval_batch_size": 1,
+    "per_device_train_batch_size": 1,
+    "gradient_accumulation_steps": 32,
+    "seed": 42,
+    "warmup_steps": 2000,
+    "do_train": true,
+    "do_eval": true,
+    "do_predict": true,
+    "pad_to_max_length": false,
+    "max_seq_length": 128,
+    "report_to": [],
+    "save_strategy": "epoch",
+    "evaluation_strategy": "epoch",
+    "logging_steps": 2500,
+    "use_fast_tokenizer": true,
+    "group_by_length": true,
+    "save_training_dynamics": true,
+    "save_training_dynamics_after_epoch": true
+}

special_tokens_map.json

@@ -0,0 +1 @@
+{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}

tokenizer_config.json

@@ -0,0 +1 @@
+{"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "bert-large-uncased", "tokenizer_class": "BertTokenizer"}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "train_loss": 0.33884849047837634,
+    "train_runtime": 68835.7532,
+    "train_samples": 392702,
+    "train_samples_per_second": 17.115,
+    "train_steps_per_second": 0.535
+}

trainer_state.json

@@ -0,0 +1,136 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.9999236061950283,
+  "global_step": 36813,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.2,
+      "learning_rate": 4.92818774595697e-05,
+      "loss": 0.6685,
+      "step": 2500
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 4.5691264757418205e-05,
+      "loss": 0.5333,
+      "step": 5000
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 4.2100652055266715e-05,
+      "loss": 0.4987,
+      "step": 7500
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 3.851003935311522e-05,
+      "loss": 0.4736,
+      "step": 10000
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8371879775853286,
+      "eval_loss": 0.42127805948257446,
+      "eval_runtime": 131.8099,
+      "eval_samples_per_second": 74.463,
+      "eval_steps_per_second": 74.463,
+      "step": 12271
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 3.491942665096372e-05,
+      "loss": 0.4506,
+      "step": 12500
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 3.132881394881222e-05,
+      "loss": 0.3355,
+      "step": 15000
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 2.7738201246660732e-05,
+      "loss": 0.327,
+      "step": 17500
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 2.4147588544509238e-05,
+      "loss": 0.3286,
+      "step": 20000
+    },
+    {
+      "epoch": 1.83,
+      "learning_rate": 2.055697584235774e-05,
+      "loss": 0.3248,
+      "step": 22500
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8537952114111055,
+      "eval_loss": 0.4055429697036743,
+      "eval_runtime": 128.0726,
+      "eval_samples_per_second": 76.636,
+      "eval_steps_per_second": 76.636,
+      "step": 24542
+    },
+    {
+      "epoch": 2.04,
+      "learning_rate": 1.6966363140206246e-05,
+      "loss": 0.2878,
+      "step": 25000
+    },
+    {
+      "epoch": 2.24,
+      "learning_rate": 1.3375750438054752e-05,
+      "loss": 0.1668,
+      "step": 27500
+    },
+    {
+      "epoch": 2.44,
+      "learning_rate": 9.785137735903255e-06,
+      "loss": 0.1662,
+      "step": 30000
+    },
+    {
+      "epoch": 2.65,
+      "learning_rate": 6.19452503375176e-06,
+      "loss": 0.1598,
+      "step": 32500
+    },
+    {
+      "epoch": 2.85,
+      "learning_rate": 2.6039123316002644e-06,
+      "loss": 0.1571,
+      "step": 35000
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8572592969943963,
+      "eval_loss": 0.5091902017593384,
+      "eval_runtime": 128.5413,
+      "eval_samples_per_second": 76.357,
+      "eval_steps_per_second": 76.357,
+      "step": 36813
+    },
+    {
+      "epoch": 3.0,
+      "step": 36813,
+      "total_flos": 8.534430377160109e+16,
+      "train_loss": 0.33884849047837634,
+      "train_runtime": 68835.7532,
+      "train_samples_per_second": 17.115,
+      "train_steps_per_second": 0.535
+    }
+  ],
+  "max_steps": 36813,
+  "num_train_epochs": 3,
+  "total_flos": 8.534430377160109e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e877f27373f3f7597260f1523617c6b316570968aa06bcaa1c3fcb48b838c4b5
+size 3119

training_dynamics/epoch0_train_idxs_[392702].pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d0be2f036cbb4178513f0ff285b3f6601e7db0e7b5b8548829b1a20196f3b4e
+size 3142315

training_dynamics/epoch0_train_logits_[392702, 3].pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6821924bb215871859ea7703b544f47a06116d3d27b36fd632b4d7398818e38
+size 4713131

training_dynamics/epoch1_train_idxs_[392702].pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6ce5f11c72d3585d24e52b785731450ab9848b24fcda9d0775ec600d9f93cef
+size 3142315

training_dynamics/epoch1_train_logits_[392702, 3].pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b0ccffeffad58992e47cbdf41cba6dec1d3904e7856838a2ad18d93d3c1eb9e3
+size 4713131

training_dynamics/epoch2_train_idxs_[392672].pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:467a5ee2a8730bbcb8291a4c8482e9bd3f657b8d4c176df846a5326d3e403ce0
+size 3142123

training_dynamics/epoch2_train_logits_[392672, 3].pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f3b33c7939a0a9e3b8ddf2ddae4be01fdf4a59d0bbaa8989b6fa6c99ed7f2ef
+size 4712811

training_dynamics_after_epoch/epoch0_after_epoch_train_idxs_[392702].pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4308434961105efbd84ef75e1b6483e64780826fb3de6753ee9e0dc72b90b58
+size 3142315

training_dynamics_after_epoch/epoch0_after_epoch_train_logits_[392702, 3].pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94472af6922857c23a87f6b25245ad2a980dc94615e75ef8756abdfe09bddc01
+size 4713131

training_dynamics_after_epoch/epoch1_after_epoch_train_idxs_[392702].pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d932165e8f0194d4227579002c66c3449d7b5c8ae67aff1953aa573a9e299cea
+size 3142315

training_dynamics_after_epoch/epoch1_after_epoch_train_logits_[392702, 3].pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:105bc0d1e6fa2b4035227fd5fcc3aea892a461505aa8d43c87cb2c4f8532c100
+size 4713131

training_dynamics_after_epoch/epoch2_after_epoch_train_idxs_[392702].pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0419fb999d1098411d63bafb8a49fedb7e5d9a34df569b899b06a21ed984ad5
+size 3142315

training_dynamics_after_epoch/epoch2_after_epoch_train_logits_[392702, 3].pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ac2abf21d06a74ba79c1c8a0d7abbdd31e3e16ef0e8b4002814b5252d953f6f
+size 4713131

val-mm_sals.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79792f7936ef432463e67def00b0fe8ef57f2de46de5be07a376d9e5d0472970
+size 10068096

validation-m_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 3.0,
+    "validation-m_accuracy": 0.8572592969943963,
+    "validation-m_loss": 0.5091902017593384,
+    "validation-m_runtime": 128.2797,
+    "validation-m_samples": 9815,
+    "validation-m_samples_per_second": 76.512,
+    "validation-m_steps_per_second": 76.512
+}

validation-mm_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 3.0,
+    "validation-mm_accuracy": 0.8581163547599675,
+    "validation-mm_loss": 0.5057684779167175,
+    "validation-mm_runtime": 129.1109,
+    "validation-mm_samples": 9832,
+    "validation-mm_samples_per_second": 76.152,
+    "validation-mm_steps_per_second": 76.152
+}